Are HingeL1, HingeL2, SigmoidCrossEntropy and Infogain loss layers implemented?

PrincetonVision / marvin

Marvin: A Minimalist GPU-only N-Dimensional ConvNets Framework

MIT License

422 stars 137 forks source link

Are HingeL1, HingeL2, SigmoidCrossEntropy and Infogain loss layers implemented? #48

Open sunformoon opened 7 years ago

sunformoon commented 7 years ago

Hi, I just downloaded the master branch of marvin. I checked the code and found that there are no implementations for the loss layers mentioned above. Did I miss something?

Thank you!

rspezialetti commented 7 years ago

Hi, i have the same problem. Are they implemented?

sunformoon commented 6 years ago

@rspezialetti Last year, I switched to pytorch for the 3d conv purpose. And tensorflow should also support the 3d conv very well.